All Posts

Grow your Virtual Assistant, Artificial Intelligence, Chatbot and Taxonomy Vocabulary

When I was checking out definitions online, I saw that it was hard to find the whole set I was looking for in one place and that most of them were pretty technical. I wanted something in layman’s terms that didn’t require a mass amount of digestion. Here is what I came up with:

AI Technologies:

  • Artificial Intelligence - Computer program (s) that create the illusion of human intelligence in machines.
  • Machine Learning - A computer program that can teach itself to improve and grow when new data is introduced.
  • Natural Language Processing – Interaction between machine and human that creates the illusion that the machine is a human. Machine being able to interpret and provide language interaction with use of terms and thesaurus to build a large language library.
  • Cognitive Computing – A computer program that mimics human thought process, often used in A.I.

The Bots:

  • Chatbot - An interactive computer program that uses an avatar to speak to users, answering questions by pulling from an enterprise knowledge management system. These programs often use a combination of natural language processing and enterprise search, but can be enhanced to use machine learning, cognitive computing and many other AI or other technology aspects. These bots can be created for a specific role such as Sales Assistant, Marketing Analyst or Customer Support.
  • Intelligent Virtual Assistant – A chatbot specializing in personal or professional organization.  This bot does tasks such as meeting organization, to do lists and hotel booking.
  • Robotic Process Automation – A bot specializing in automating processes across multiple systems. Ensuring the knowledge management its cross organization creates the opportunity to make processes more efficient through automation, freeing employee time for more interesting tasks.

SEO and Taxonomy:

  • Enterprise Search – Search ability to pull from areas across the entire company for full access to content.
  • Semantic Search – Search that is contextualized, focusing on keywords, term relationships and user intent to provide a more insightful search result.
  • Screen Scraping - Collecting all data from an assigned set of screens. Often used in catalog scraping. Used for data analysis, data normalization and data fill.
  • Taxonomy – A data architecture that allows the classification of things. For example, when you go to a retail site they will often have a taxonomy of products, starting with the high level basics and dropping down to more specifics as you go deeper into the taxonomy and finally arriving at a final category node at the bottom of the taxonomy which holds items that fit into that category.
  • Ontology – This one killed me…I kept getting that it was about metaphysics and the meaning of existence. Ontology, in the world of information science, is a collection of taxonomies and relationships. Ontology goes deeper into relationships by adding metadata describing the relationship and allowing it to be more complex.
  • Attributes – Descriptive terms used to describe an item.  There are many variables for attributes. They can be global (used across all items in a system) or category specific (used for a specific category, for example attribute: [Watts] being used for the category: <Lightbulbs>). They can be internal (for use of reporting) or external (used on a website or mobile app to customers). They can be navigational (used for filtering down to a specific set of items in a taxonomy) or for display use. You ideally always have an Attribute Name and Attribute Value (Example: Color and Red)
  • Variants – A similar set of items with one attribute that creates the difference. For example, you can have a set of shoes with the size being the variant. They still are grouped together because they are, otherwise, the same.
  • Schema – The design of taxonomy and category specific attribution.  Product taxonomy is organized by is-ness because the bottom level category node will have category specific attribution. This was previously mentioned in this example: attribute- [Watts] being used for the category- <Lightbulbs>.
  • Relationships – How different things in the taxonomy are set to be associated. There are many instances of relationships. The most basic is Parent-Child. The category <Hand Tools> may be a parent to the category <Hammers>. Meanwhile <Hammers> may be a sibling to <Screwdrivers>. Relationships can be created to build different experiences, such as Accessories. A phone case is an accessory to a cell phone.

System capabilities and processes:

  • Governance – A system of workflows and approving parties put in place to ensure consistency, control, ownership and accountability. Taxonomy without governance will quickly go out of control and need a mass cleanup.
  • Multi-Device – This is used as a descriptor for a program that can be used across multiple devices such as computer and mobile app.
  • Dashboard – A user interface in a computer program designed for a specific user of the data to make use more efficient.
  • Core Algorithm – A programmed process to mine data, often searching for a specific pattern set, and using this data to solve a problem. Often seen in machine learning.
  • Data Mining – Analyzing large sets of data for patterns and information
  • Pattern Recognition – A computer program ability that focuses on the recognition of patterns often uses in algorithms.
  • Process Automation – Automating a process through computers and computer programs to accomplish a function with less human error and faster speed.
  • Avatar - An icon, often in the form of a person, that acts as the face of a technology. When engaged with a chatbot, the user is often ‘chatting’ with an avatar.

I could have gone on but will stop for now.  Have I missed any definitions you'd like to see?  Do you think I got any of them wrong?  I'd love to hear your ideas.

For a look into how we use customer data models, product data models, content models, and knowledge architecture to create a framework for unified commerce download our whitepaper: Attribute-Driven Framework for Unified Commerce

Chantal Schweizer
Chantal Schweizer
Chantal Schweizer is a taxonomy professional with over 10 years of experience in Product Information and Taxonomy. Prior to joining Earley Information Science, Chantal worked on the Product Information team at Grainger for 9 years, Schneider Electric’s PIM team for 2 years and had some previous work in PIM consulting.

Recent Posts

Conversation with ChatGPT on Enterprise Knowledge Management

In another article, I discussed my research into ChatGPT and the interesting results that it produced depending on the order in which I entered queries. In some cases, the technology seemed to learn from a prior query, in others it did not. In many cases, the results were not factually correct.

The Future of Bots and Digital Transformation – Is ChatGPT a Game Changer?

Digital assistants are taking a larger role in digital transformations. They can improve customer service, providing more convenient and efficient ways for customers to interact with the organization. They can also free up human customer service agents by providing quick and accurate responses to customer inquiries and automating routine tasks, which reduces call center volume. They are available 24/7 and can personalize recommendations and content by taking into consideration role, preferences, interests and behaviors. All of these contribute to improved productivity and efficiency. Right now, bots are only valuable in very narrow use cases and are unable to handle complex tasks. However, the field is rapidly changing and advances in algorithms are having a very significant impact.

[February 15] Demystifying Knowledge Graphs – Applications in Discovery, Compliance and Governance

A knowledge graph is a type of data representation that utilizes a network of interconnected nodes to represent real-world entities and the relationships between them. This makes it an ideal tool for data discovery, compliance, and governance tasks, as it allows users to easily navigate and understand complex data sets. In this webinar, we will demystify knowledge graphs and explore their various applications in data discovery, compliance, and governance. We will begin by discussing the basics of knowledge graphs and how they differ from other data representation methods. Next, we will delve into specific use cases for knowledge graphs in data discovery, such as for exploring and understanding large and complex datasets or for identifying hidden patterns and relationships in data. We will also discuss how knowledge graphs can be used in compliance and governance tasks, such as for tracking changes to data over time or for auditing data to ensure compliance with regulations. Throughout the webinar, we will provide practical examples and case studies to illustrate the benefits of using knowledge graphs in these contexts. Finally, we will cover best practices for implementing and maintaining a knowledge graph, including tips for choosing the right technology and data sources, and strategies for ensuring the accuracy and reliability of the data within the graph. Overall, this webinar will provide an executive level overview of knowledge graphs and their applications in data discovery, compliance, and governance, and will equip attendees with the tools and knowledge they need to successfully implement and utilize knowledge graphs in their own organizations. *Thanks to ChatGPT for help writing this abstract.